find_channels

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It reveals important behavioral traits: results are ranked by prevalence and split by growth stage, and a cohort_size field is returned with possible warnings that should be honored. It does not disclose return format in full (e.g., exact JSON structure) or any side effects, but for a read-only-style tool this is sufficient. The explicit warning handling instruction adds meaningful transparency beyond just 'returns channels.'

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise yet comprehensive, using three short paragraphs with clear structure. It front-loads the tool's primary purpose and then details parameters and output handling in an organized manner. Every sentence adds value, with no filler or repetition of schema information. It is long enough to be useful but not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (10 parameters, no output schema), the description covers the essential aspects: purpose, input parameters with allowed values, and output expectations (cohort_size, warnings). It does not specify the full response format or how to interpret all fields, but the named example companies and stage split are mentioned. A minor gap is the lack of an example invocation, but the description is largely complete for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has zero description coverage for all 10 parameters, so the description must compensate. It provides semantic meaning for most parameters: sector (group/raw), business_model (list of values), era (specific ranges), trust_burden, virality, cac_ceiling, category_play (with enums), and explains the 'stage' parameter's role in ranking. However, it leaves 'status' and 'top' without explanation, but 'top' is intuitive (default 12) and 'status' may be self-evident. Overall, strong compensation for the missing schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as 'PRIMARY TOOL' and states its specific function: return channels used by comparable Indian startups, ranked by prevalence and split by growth stage. It distinguishes itself from sibling tools by emphasis on 'used by comparable Indian startups' and the ranking/splitting behavior, which is unique and not mentioned in sibling names. The verb 'return' is precise.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Given a marketing situation' and explicitly lists the subset of parameters that can be passed, which guides when to use the tool. It also instructs to 'Always report the returned cohort_size and honor any warning,' which is a usage requirement. However, it does not explicitly mention alternatives or when not to use this tool, unlike a tool that says 'use X instead.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.